Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting
Not on the map. Why?
Abstract (arXiv)
The integration of Fourier transform and deep learning opens new avenues for time series forecasting. We reconsider the Fourier transform from a basis functions perspective. Specifically, the real and imaginary parts of the frequency components can be regarded as the coefficients of cosine and sine basis functions at tiered frequency levels, respectively. We find that existing Fourier-based methods face inconsistent starting cycles and inconsistent series length issues. They fail to interpret frequency components precisely and overlook temporal information. Accordingly, the novel Fourier Basis Mapping (FBM) method addresses these issues by integrating time-frequency features through Fourier basis expansion and mapping in the time-frequency space. Our approach extracts explicit frequency features while preserving temporal characteristics. FBM supports plug-and-play integration with various types of neural networks by only adjusting the first initial projection layer for better performance. First, we propose FBM-L, FBM-NL, and FBM-NP to enhance linear, MLP-based, and Transformer-based models, respectively, demonstrating the effectiveness of time-frequency features. Next, we propose a synergetic model architecture, termed FBM-S, which decomposes the seasonal, trend, and interaction effects into three separate blocks, each designed to model time-frequency features in a specialized manner. Finally, we introduce several techniques tailored for time-frequency features, including interaction masking, centralization, patching, rolling window projection, and multi-scale down-sampling. The results are validated on diverse real-world datasets for both long-term and short-term forecasting tasks with SOTA performance.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 35 of its 54 references that are in the map. First posted on arXiv 13 Jul 2025.
Builds on
35 of 54 references.
References · 35
- 2017Attention Is All You Needcited by 60,361
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
- 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
- 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
- 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
- 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
- 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
- 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
- 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
- 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
23 more
- 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
- 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 346
- 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
- 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 269
- 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
- 2023FITS: Modeling Time Series with 10k Parameterscited by 195
- 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 174
- 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 172
- 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
- 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 160
- 2022FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecastingcited by 147
- 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
- 2023FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspectivecited by 127
- 2024Is Mamba Effective for Time Series Forecasting?cited by 114
- 2024DUET: Dual Clustering Enhanced Multivariate Time Series Forecastingcited by 107
- 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 104
- 2024Timer-XL: Long-Context Transformers for Unified Time Series Forecastingcited by 87
- 2017Dilated Recurrent Neural Networkscited by 83
- 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
- 2023BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basiscited by 41
- 2023Graph Deep Learning for Time Series Forecastingcited by 26
- 2020Spatiotemporal Attention for Multivariate Time Series Prediction and Interpretationcited by 18
- 2023Adaptive Dependency Learning Graph Neural Networkscited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.